You may wish to apply some sanity checking bounds on the responses from subject matter experts. This function applies a set of predefined transformations to the scenario and capability responses. Review these assumptions carefully before using them in your own analysis.
clean_answers(scenario_answers, capability_answers)
| scenario_answers | Scenario answers dataframe. |
|---|---|
| capability_answers | Capability answers dataframe. |
A list of modified scenarios and capabilities.
Make the following assumptions/modifications
minimum capacity is 5% (we've thought about it - 90% CI)
maximum capacity is 95% (we're just about the best - 90% CI)
minimum loss is 1000 dollars (both low and high)
scale all impact into thousands of dollars (make normal decomposition easier, and is in line of the scale of a strategic analysis)
set a minimum frequency of once per 10 years (0.1)
data(mc_capability_answers) data(mc_scenario_answers) clean_answers(mc_scenario_answers, mc_capability_answers)#> $capabilities #> # A tibble: 300 x 5 #> sme capability_id low high date #> <chr> <chr> <dbl> <dbl> <date> #> 1 Jimmy Jennings CAP-01 0.1 0.4 2018-09-10 #> 2 Jimmy Jennings CAP-02 0.1 0.4 2018-09-10 #> 3 Jimmy Jennings CAP-03 0.1 0.4 2018-09-10 #> 4 Jimmy Jennings CAP-04 0.1 0.4 2018-09-10 #> 5 Jimmy Jennings CAP-05 0.1 0.4 2018-09-10 #> 6 Jimmy Jennings CAP-06 0.1 0.4 2018-09-10 #> 7 Jimmy Jennings CAP-07 0.1 0.4 2018-09-10 #> 8 Jimmy Jennings CAP-08 0.1 0.4 2018-09-10 #> 9 Jimmy Jennings CAP-09 0.1 0.4 2018-09-10 #> 10 Jimmy Jennings CAP-10 0.1 0.4 2018-09-10 #> # … with 290 more rows #> #> $scenarios #> # A tibble: 280 x 7 #> sme scenario_id freq_low freq_high imp_low imp_high date #> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <date> #> 1 Jimmy Jennings RS-01 10 40 1000 3000000 2018-09-10 #> 2 Marsha Watson RS-01 10 40 1000 3000000 2018-09-10 #> 3 Natalie Wade RS-01 10 40 1000 3000000 2018-09-10 #> 4 Ray Evans RS-01 0.1 40 1000 3000000 2018-09-10 #> 5 Theresa Fowler RS-01 10 40 1000 3000000 2018-09-10 #> 6 Jimmy Jennings RS-02 10 40 1000 3000000 2018-09-10 #> 7 Marsha Watson RS-02 10 40 1000 3000000 2018-09-10 #> 8 Natalie Wade RS-02 10 40 1000 3000000 2018-09-10 #> 9 Ray Evans RS-02 10 40 1000 3000000 2018-09-10 #> 10 Theresa Fowler RS-02 10 40 1000 3000000 2018-09-10 #> # … with 270 more rows #>